formatting-build-output

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONNO_CODE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to process and format compiler logs which may contain untrusted data from source code comments or third-party error messages.
  • Ingestion points: Standard output and error logs from xcodebuild and swift build commands (SKILL.md).
  • Boundary markers: The TOON format uses structured keys but lacks explicit delimiters or instructions to ignore embedded prompts within the 'message' fields.
  • Capability inventory: Command execution of build tools and the xcsift utility.
  • Sanitization: No evidence of input sanitization or output escaping for log content is provided.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform command-line operations, specifically piping build output from standard development tools into the xcsift utility.
  • [NO_CODE]: The skill package contains no scripts or binary assets; it functions as a documentation-only extension providing usage instructions for an external tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 08:18 PM